Self-calibration of a camera from video of a walking human

Analysis of human activity from a video camera is simplified by the knowledge of the camera's intrinsic and extrinsic parameters. We describe a technique to estimate such parameters from image observations without requiring measurements of scene objects. We first develop a general technique for calibration using vanishing points and vanishing line. We then describe a method for estimating the needed points and line by observing the motion of a human in the scene. Experimental results, including error estimates, are presented.

[1]  Antonio Criminisi,et al.  Creating Architectural Models from Images , 1999, Comput. Graph. Forum.

[2]  B. Caprile,et al.  Using vanishing points for camera calibration , 1990, International Journal of Computer Vision.

[3]  Søren I. Olsen,et al.  Epipolar Line Estimation , 1992, ECCV.

[4]  Ramakant Nevatia,et al.  Segmentation and tracking of multiple humans in complex situations , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[5]  Roberto Cipolla,et al.  Camera Calibration from Vanishing Points in Image of Architectural Scenes , 1999, BMVC.

[6]  O. Faugeras.  Three-dimensional computer vision: a geometric viewpoint , 1993 .

[7]  Ian D. Reid,et al.  Single View Metrology , 2000, International Journal of Computer Vision.

[8]  Alex Pentland,et al.  Pfinder: real-time tracking of the human body , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.